Qwen3.6 35B A3B vs Qwen3.7 Plus Preview
Wins 0 of 8 areas
—
Wins 8 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Long documents · Following instructions
Qwen3.7 Plus Preview is the stronger all-rounder.
Scores updated · 49 tests both models report · How we compare
Where each one wins
Tests won in each of the eight areas we test. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
- CodingWriting and fixing software07Qwen3.7 Plus Preview7 of 7 tests
- ReasoningHard problems that need careful thinking03Qwen3.7 Plus Preview3 of 3 tests
- Images and chartsUnderstanding pictures, charts and video03Qwen3.7 Plus Preview3 of 3 tests
- MathCompetition and research-level math03Qwen3.7 Plus Preview3 of 3 tests
- AgentsCarrying out multi-step tasks on its own13Qwen3.7 Plus Preview3 of 4 tests
- FactsGetting facts right instead of making them up02Qwen3.7 Plus Preview2 of 2 tests
- Long documentsFinding answers in very long texts01Qwen3.7 Plus Preview1 of 1 test
- Following instructionsDoing exactly what it is asked01Qwen3.7 Plus Preview1 of 1 test
Long documents and following instructions rest on a single test each.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
Qwen3.7 Plus Preview costs 24% less for the same work.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Qwen3.7 Plus Preview pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+22.8points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+16.1points ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+14points ahead
Where Qwen3.6 35B A3B pulls ahead
- Real work tasks from 44 professionsGDPVal+6.2points ahead
Every test, side by side
All 49 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3.7 Plus Preview
- Terminal-Bench 2.1Qwen3.7 Plus Preview by 16.144.961+16.1
- Terminal-Bench HardQwen3.7 Plus Preview by 12.234.847+12.2
- SciCodeQwen3.7 Plus Preview by 9.536.646.1+9.5
- LiveCodeBench v6Qwen3.7 Plus Preview by 9.280.489.6+9.2
- SWE-bench MultilingualQwen3.7 Plus Preview by 8.667.275.8+8.6
- SWE-bench ProQwen3.7 Plus Preview by 8.149.557.6+8.1
- SWE-bench VerifiedQwen3.7 Plus Preview by 4.373.477.7+4.3
AgentsQwen3.7 Plus Preview
- MCP AtlasQwen3.7 Plus Preview by 10.462.873.2+10.4
- τ-Bench V3 · BankingQwen3.7 Plus Preview by 8.29.317.5+8.2
- GDPValQwen3.6 35B A3B by 6.219.613.4+6.2
- Terminal-Bench 4.0Qwen3.7 Plus Preview by 101+1
ReasoningQwen3.7 Plus Preview
- Humanity's Last ExamQwen3.7 Plus Preview by 13.422.235.6+13.4
- CritPtQwen3.7 Plus Preview by 8.80.39.1+8.8
- GPQA DiamondQwen3.7 Plus Preview by 5.984.190+5.9
FactsQwen3.7 Plus Preview
- AA-Omniscience · Non-hallucinationQwen3.7 Plus Preview by 22.849.572.3+22.8
- AA-Omniscience · AccuracyQwen3.7 Plus Preview by 3.718.822.5+3.7
Images and chartsQwen3.7 Plus Preview
- CharXiv (RQ)Qwen3.7 Plus Preview by 7.97885.9+7.9
- MMMU-ProQwen3.7 Plus Preview by 5.57580.5+5.5
- OCRBenchv2Qwen3.7 Plus Preview by 1.665.567.1+1.6
MathQwen3.7 Plus Preview
- FrontierMath Tiers 1-3 (v2)Qwen3.7 Plus Preview by 1420.434.4+14
- HMMT Feb. 2026Qwen3.7 Plus Preview by 9.383.692.9+9.3
- IMOAnswerBenchQwen3.7 Plus Preview by 7.178.986+7.1
Long documentsQwen3.7 Plus Preview
- AA-LCRQwen3.7 Plus Preview by 1.371.773+1.3
Following instructionsQwen3.7 Plus Preview
- IFBenchQwen3.7 Plus Preview by 13.664.478+13.6
Other results25 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- DeepPlanningQwen3.7 Plus Preview by 36.425.962.3+36.4
- AA-OmniscienceQwen3.7 Plus Preview by 23.3-22.21.1+23.3
- SimpleVQAQwen3.7 Plus Preview by 22.858.981.7+22.8
- MCPMarkQwen3.7 Plus Preview by 21.73758.7+21.7
- Terminal-Bench 2.0Qwen3.7 Plus Preview by 18.851.570.3+18.8
- Artificial Analysis Coding IndexQwen3.7 Plus Preview by 1441.955.9+14
- Claw Eval (pass@3)Qwen3.7 Plus Preview by 12.75062.7+12.7
- NL2RepoQwen3.7 Plus Preview by 11.729.441.1+11.7
- VITA-BenchQwen3.7 Plus Preview by 1035.645.6+10
- QwenClawBenchQwen3.7 Plus Preview by 9.252.661.8+9.2
- BFCLv4Qwen3.7 Plus Preview by 7.96572.9+7.9
- AA IntelligenceQwen3.7 Plus Preview by 718.225.2+7
- HLE-DiamondQwen3.7 Plus Preview by 76.913.9+7
- SuperGPQAQwen3.7 Plus Preview by 6.764.771.4+6.7
- GDP (Surge AI)Qwen3.7 Plus Preview by 5.66.612.2+5.6
- LVBenchQwen3.7 Plus Preview by 4.871.476.2+4.8
- AA Agentic IndexQwen3.7 Plus Preview by 4.71519.7+4.7
- MMLU-ProQwen3.7 Plus Preview by 3.385.288.5+3.3
- τ²-Bench Telecom (AA run)Qwen3.6 35B A3B by 2.395.393+2.3
- VideoMMMUQwen3.7 Plus Preview by 1.783.785.4+1.7
- RealWorldQAQwen3.7 Plus Preview by 1.685.386.9+1.6
- IFEvalQwen3.7 Plus Preview by 1.593.194.6+1.5
- OmniDocBench 1.5Qwen3.7 Plus Preview by 1.589.991.4+1.5
- MLVUQwen3.7 Plus Preview by 1.286.287.4+1.2
- MMLU-ReduxQwen3.7 Plus Preview by 1.293.394.5+1.2
Questions people ask
Which is better, Qwen3.6 35B A3B or Qwen3.7 Plus Preview?
Qwen3.7 Plus Preview wins all eight areas we test: coding, agents, reasoning, facts, images and charts, math, long documents and following instructions. Qwen3.6 35B A3B wins none.
Which is better for coding?
Qwen3.7 Plus Preview. It wins 7 of the 7 coding tests both models report; Qwen3.6 35B A3B wins none.
Which is cheaper?
Qwen3.6 35B A3B costs $0.38 per million input tokens and $2.25 per million output tokens; Qwen3.7 Plus Preview costs $0.40 and $1.60. That makes Qwen3.7 Plus Preview about 24% cheaper for the same work.
How do you compare the two?
We use the 49 benchmark tests both models have published scores on. The verdict counts the 24 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 25 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.